Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Failure Attribution on Who&When (HC)
Loading...
22.99
Accuracy (%)
StepFinder
2.0652
7.4976
12.93
18.3624
Jun 2, 2026
Accuracy (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (%)
StepFinder
2026.06
22.99
StepFinder
Category=Sequential, E...
2026.06
22.99
AgenTracer
2026.06
20.68
AgenTracer
evaluation with ground...
2026.06
20.68
CDC-MAS
2026.06
18.2
BiGRU
Category=Sequential, L...
2026.06
12.64
TCN
Category=Sequential, L...
2026.06
10.35
Transformer
Category=Sequential, L...
2026.06
9.19
Step-by-Step
Category=LLM-based, LL...
2026.06
7.47
Step-by-Step (G)
Category=LLM-based, LL...
2026.06
6.9
Binary Search
Category=LLM-based, LL...
2026.06
6.32
Binary Search (G)
Category=LLM-based, LL...
2026.06
5.75
Random
Category=Baseline
2026.06
4.6
All-at-Once (G)
Category=LLM-based, LL...
2026.06
4.6
All-at-Once
Category=LLM-based, LL...
2026.06
2.87
Feedback
Search any
task
Search any
task